Image restoration using a kNN-variant of the mean-shift - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Image restoration using a kNN-variant of the mean-shift

Résumé

The image restoration problem is addressed in the variational framework. The focus was set on denoising. The statistics of natural images are consistent with the Markov random field principles. Therefore, a restoration process should preserve the correlation between adjacent pixels. The proposed approach minimizes the conditional entropy of a pixel knowing its neighborhood. The conditional aspect helps preserving local image structures such as edges and textures. The statistical properties of the degraded image are estimated using a novel, adaptive weighted k-th nearest neighbor (kNN) strategy. The derived gradient descent procedure is mainly based on meanshift computations in this framework.
Fichier principal
Vignette du fichier
ICIP08mod.pdf (270.64 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00379329 , version 1 (28-04-2009)
hal-00379329 , version 2 (27-10-2010)

Identifiants

  • HAL Id : hal-00379329 , version 2

Citer

Cesario Vincenzo Angelino, Eric Debreuve, Michel Barlaud. Image restoration using a kNN-variant of the mean-shift. IEEE International Conference on Image Processing, Oct 2008, San Diego, California, United States. ⟨hal-00379329v2⟩
137 Consultations
354 Téléchargements

Partager

Gmail Facebook X LinkedIn More